Moderate exercise contributes to health, but excessive exercise may lead to physicalinjury or even endanger life. It is pressing for a device that can detect the intensity of exercise.Therefore, in order to enable rea...Moderate exercise contributes to health, but excessive exercise may lead to physicalinjury or even endanger life. It is pressing for a device that can detect the intensity of exercise.Therefore, in order to enable real-time detection of exercise intensity and mitigate the risks of harmfrom excessive exercise, a exercise intensity monitoring system based on the heart rate variability(HRV) from electrocardiogram (ECG) signal and linear features from phonocardiogram (PCG)signal is proposed. The main contributions include: First, accurate analysis of HRV is crucial forsubsequent exercise intensity detection. To enhance HRV analysis, we propose an R-peak detectorbased on encoder-decoder and temporal convolutional network (TCN). Experimental resultsdemonstrate that the proposed R-peak detector achieves an F1 score exceeding 0.99 on real high-intensity exercise ECG datasets. Second, an exercise fatigue monitoring system based on multi-signal feature fusion is proposed. Initially, utilizing the proposed R-peak detector for HRV extractionin exercise intensity detection,which outperforms traditional algorithms, with the system achieving a classification performance of 0.933 sensitivity, 0.802 specificity, and 0.960 accuracy. To further improve the system, we combine HRV with the linear features of PCG. Our exercise intensitydetection system achieves 90.2% specificity, 96.7% recall, and 98.1% accuracy in five-fold cross-validation.展开更多
基金the National Natural Science Foundation of China(No.62301056)the Fundamental Research Funds for Central Universities(No.2022QN005).
文摘Moderate exercise contributes to health, but excessive exercise may lead to physicalinjury or even endanger life. It is pressing for a device that can detect the intensity of exercise.Therefore, in order to enable real-time detection of exercise intensity and mitigate the risks of harmfrom excessive exercise, a exercise intensity monitoring system based on the heart rate variability(HRV) from electrocardiogram (ECG) signal and linear features from phonocardiogram (PCG)signal is proposed. The main contributions include: First, accurate analysis of HRV is crucial forsubsequent exercise intensity detection. To enhance HRV analysis, we propose an R-peak detectorbased on encoder-decoder and temporal convolutional network (TCN). Experimental resultsdemonstrate that the proposed R-peak detector achieves an F1 score exceeding 0.99 on real high-intensity exercise ECG datasets. Second, an exercise fatigue monitoring system based on multi-signal feature fusion is proposed. Initially, utilizing the proposed R-peak detector for HRV extractionin exercise intensity detection,which outperforms traditional algorithms, with the system achieving a classification performance of 0.933 sensitivity, 0.802 specificity, and 0.960 accuracy. To further improve the system, we combine HRV with the linear features of PCG. Our exercise intensitydetection system achieves 90.2% specificity, 96.7% recall, and 98.1% accuracy in five-fold cross-validation.
